You could call me a noob in this field but the doom news and doom yt videos about AI sparked the question in me.
Why would we give the AI an ability to be evil, selfish, destructive, deceiving?
If that code doesn’t exist, then ai cannot form it? Or? Why would we purposely risk our well being, well being of humanity in giving Ai the ability to be destructive to us?
For me it doesn’t make sense.
Why not make AI or agents as benevolent as possible?
[link] [comments]